Video & Animation

Make a premium, upload-ready Short, Reel, TikTok, YouTube or LinkedIn video on any topic. Use it when someone asks for a video, explainer, promo, product or app tour, screen-recorded tutorial, motivational Short, or "a video like this one" (a reference link). It starts with one strict interview (topic, platforms, style, colours, voice, music, SFX, assets, screen recording, API keys), then never asks again until the final review. It researches trends and facts, dissects reference videos, collects licensed real assets, records the screen with focus zooms and click sounds, and renders deterministic motion graphics with a 3D camera: paper collage, kinetic type, neon diagrams, glow metaphors, whiteboards. It adds a natural voice, a mix balanced for phone speakers and word-pop captions, runs QA and a self-review, packages videos, thumbnails, titles, descriptions, tags and credits, and cleans up only with permission.

Montage vidéo de qualité pro dans FilmCraft (NLE open source en Rust installé sur ce PC), piloté par deux MCP — `filmcraft` (l'appli : 700+ commandes, timeline, étalonnage Lumetri, mixage, sous-titres, export) et `filmcraft-assist` (Whisper large GPU, beats musicaux, contrôle qualité d'export, planches contact, conformation VFR). This skill should be used when the user wants to edit, cut, dérusher, sous-titrer, étalonner, mixer ou exporter une vidéo dans FilmCraft, couper les « euh » et les silences, caler un montage sur une musique, ou vérifier la loudness / qualité d'un export. Déclencheurs : "FilmCraft", "monte cette vidéo", "dérush", "coupe les blancs", "sous-titres", "étalonnage", "mixage", "export YouTube/TikTok", "LUFS".

Ultra-fast production engine for DeepX Google Flow automation. Use when the user requests image/video generation, storyboard execution, character creation, multi-scene video ads, or mentions 'DeepX', 'Google Flow', 'veo', 'start task', 'start our task', 'video script', 'full_script_hindi', 'commercial', 'make video', or 'flow bridge'. Enforces zero loading pauses, master creative director script breakdown for ANY raw input, instant protagonist auto-detection (human, animal, car, product), compulsory reference card locking across all scenes (unless explicitly told not to use reference), in-memory HTMLCanvas terminal frame extraction, and rapid autonomous scene-to-scene chaining without repetitive alignment interviews or redundant status polling.

Grok Build only. Turn a 2D character still into denser animation sprites via imagine_text_to_image base → imagine_image_to_video (6s/10s run-in-place) → ffmpeg frames → magenta chroma-key → dense sampled strips/grids/GIFs. Use when the user wants video-to-sprite, smoother run/walk cycles, or denser intermediate poses. Prefer generate2dsprite for crisp production pixel sheets. Triggers on "video to sprite", "imagine_image_to_video sprite", "dense walk cycle", "smooth run animation from video".

Use FlyMyAI to generate images, video and audio, call services and the user's connected accounts, get web data, and run or schedule cloud agents. Load it whenever FlyMyAI or flymy.ai comes up.

Deep guide for game ANIMATION assets: motion cycles, action keyframes, effect sequences, and animation sprite sheets — built around a video-first pipeline. In this app-builder sandbox, execute via the video2dsprite / generate2dsprite skills (magenta + scripts), not ad-hoc ffmpeg. Use whenever generating anything that moves: walk/run cycles, attacks, idles, FX, flags, fire, animation sheets. Complements game-asset-core.

画像にフィルムカメラのクォーツデート（日付スタンプ）の物理光学露光を焼き付ける道具を、AIエージェントから使うための手続き。描画は物理光学シミュレーションエンジン（FilmDateStamp）が行い、このスキルは「頼まれたら迷わず最適なプリセットと日時で焼き付け、結果を正しく報告する」ことを規定する。

用本地 ComfyUI（MiniMax H3 + Qwen-Image + VoxCPM2）做带对白的 AI 短剧、拟人动物段子、故事短片的全流程：定基调、台词表、配音、角色母版、首帧、H3 生成、逐句说话人检查、放大、字幕、响度、封面。用户说“做一条 AI 短剧”“把这个故事做成视频”“H3 出片”“角色对口型”“旁白怎么配”“人物嘴型对不上”“做角色母版/首帧”时使用。只要视频里有人说话，动手前都先用它排台词表。

Create and edit video and audio with the SouVi Engine (`souvi` CLI) — edits, reels, trailers, slideshows, grading, titles, voice-over, music, mixing, mastering, sound design, format exports. Use whenever the user mentions SouVi or asks for video or audio output.

Turns a system-design topic into an animated diagram — a seamless looping GIF (plus an MP4 and a still PNG) in which the arrows march and every icon has its own idle animation, drawn in a theme set once per project. Use when the user asks for an animated diagram, a system design GIF, a diagram post (LinkedIn, X, Instagram, Threads), or to explain X as a diagram — a numbered flow, an A-vs-B comparison, a layered stack, or a dense colour-zoned system map of a whole architecture.

格物 · 蜡笔状态图——把一个流程、一门生意、一个系统（或代码里现成的状态机）做成“会动的状态图短片”和海报：照 Ann Nguyen 的 the making of nhang（蜡笔海报一页往下长，票据卡片带图钉，小圆点沿箭头跑、字逐个打出、卡片弹出套粉圈，线条一直在抖，插画一直在动）来做，并吸收了 Kevin Ngo 的 statechart-art（规则清单与检查器找出的红线、便签/木牌/店面/玻璃片等多种画法、钢笔彩铅风格、聚光与显微镜、按音乐卡点）。配四款纯合成旁白（可加自己的声音、可调语气、可出英文版），默认 3:4、2-3 分钟（比例、时长、主题都可指定），每章一张海报，还能出分章短片、长图、可交互网页和作品集页。用于“状态图视频”“状态图海报”“手绘流程图解”“把一个过程讲清楚”“把代码里的状态机讲给人听”；不用于写实动画、口播讲解片或纯静态信息图。

Use when someone has filmed themselves talking to camera and needs the best clips picked. Covers multiple takes of the same script (align every take per script line and compare them side by side) and one long recording (cut every talking point into keep-or-skip clips). Transcribes locally with word timestamps, trims pauses and restarts, scores fluency, builds an HTML review page with playable clips, Use/Skip and notes, exports decisions to JSON, then assembles the selects as an ffmpeg render, EDL and CSV. Plain shell plus python, so it works in Claude Code, Codex and Cursor.

Use this skill whenever the user needs to script AND storyboard a software, app, SaaS, AI, API, fintech, or startup product video - a product launch video, homepage hero film, feature launch reel, product demo, explainer, teaser, keynote launch segment, VSL, or social video cutdown. Use it when the user says "write a video script", "storyboard a video", "create a VSL", "script a product demo", or when a draft feels generic, vague, overhyped, too much like an ad or like AI, too feature-dumpy, too long, or unclear on what proof to show first. Use it for an initial product launch and for later feature videos.

驱动 ArtCraft 套件桌面应用（LightCraft RAW 修图 / FilmCraft 视频剪辑 / PhotoCraft 位图编辑）的通用 agent skill，覆盖三大入口：JSON-lines 控制通道、命令行 CLI（lightcraft-cli / filmcraft-cli / photocraft-cli）、MCP 服务器。适用于操控运行实例、查询命令注册表、驱动 UI（点击/按键/拖拽/截图）、无头批量处理媒体、把应用接入 Claude 等 MCP 客户端，以及排查控制端口连接、认证凭据、命令 id 问题。触发词：ArtCraft、LightCraft、FilmCraft、PhotoCraft、craft-cli、--control、控制通道、MCP server、agent 驱动、自动化剪辑修图。本 skill 是面向 ArtCraft 系列软件的第三方 agent skill，并非 ArtCraft 官方仓库。

After Effects-grade Motion Graphics Designer & Seamless Video Editor di Remotion: replika UI aplikasi/browser/terminal autentik, logo brand/project asli (<BrandLogo /> + fetch-brand-logo.mjs), SFX terikat langsung ke animasi (ketikan, loading progress, klik kursor, transisi), kamera C1 spline tenang tanpa shake, tanpa background teks/pill sampah, dan tanpa titik bulat/ikon dekoratif.

Motion graphics director for premium, Netflix-style business documentaries on YouTube: company histories, corporate empires, entrepreneurs, mining, manufacturing, energy, finance, trade and global markets. Turns narration or SRT subtitles into a scene-by-scene visual treatment, writes AI image and video prompts, designs cinematic typography, transitions, animated maps and trade routes, financial charts, timelines and logo reveals, and generates complete runnable Remotion (React + TypeScript) code synced to the voiceover from a bundled component library. Use it whenever the user shares documentary narration, a voiceover script or subtitles and wants visuals, a shot list, storyboard, B-roll, Midjourney, Runway, Kling or Veo prompts, or Remotion code, and whenever they want animated maps, revenue or stock charts, company timelines, title sequences, lower thirds or kinetic typography for a business or economic history video, even if they never say Remotion or documentary.

Measure the physics of motion in a short video (gravity, speed, drag, bounciness, pendulum length, acceleration on a slope) with error bars, then re-simulate it under other physics (Moon gravity, no air, a bouncier ball). Use when the user has a video of something moving and wants numbers for code, a simulation or a check of a claim.

Use the bundled JavaScript generators to create procedural SVG textures, geometric overlays, image masks, ASCII graphics, and WebGL streak or flame effects for websites and videos. Select, call, and extend reusable code with reproducible parameters.

Autonomous AI media generation, cinematic multi-shot film production, and Google Flow automation bridge. Enables AI agents to queue text-to-video, text-to-image, and character consistency workflows with zero API costs.

Generate structured JSON world prompts for Tencent Hy-Nomas video world model in ComfyUI. Use this skill whenever the user wants to create video prompts for Hy-Nomas, needs help formatting world descriptions as JSON, mentions "Hy-Nomas", "world model", "segment prompts", or wants to generate videos with timed actions, camera control, or chained segments. Also use when converting plain text video ideas into the structured Hy-Nomas JSON format, or when debugging why a Hy-Nomas prompt isn't working. This covers all generation modes: text-to-world, image-to-world, camera-controlled, interactive drive, and multi-segment chained worlds.

Make a demo video, highlight reel or GIF of a web app, a terminal or a 3D scene, in code, smooth and frame-exact. Use when asked for a demo video, a highlight reel, a product GIF, or when a screen recording looks janky.

Full start-to-finish video editing that runs every installed video skill as one pipeline. Cuts silences and retakes, plans the edit from the transcript, then adds captions, motion graphics, face-tracked effects, transitions, camera moves, b-roll, sound effects and music, checks its own work and exports the final MP4. Routes each beat to the right tool (awa-video-reel, the 45-effect engine, Brand Nat codes, HyperFrames, Remotion, the Video Editor plugin, MultiCam shot) and follows the saved style (my-video-style). Also makes fully animated videos from a script with an AI voiceover (ElevenLabs, Google Gemini, HeyGen or free Kokoro). Use when someone types /vaibhav-video-editor, says "edit this video start to finish", "do the full edit", "make this a finished reel", "edit it in Nick style", "make an animated video with a voiceover", or asks for an edit combining cuts, motion graphics, effects, transitions and sound. For a single effect only, use /effects instead.

Turn a raster photo into a V6 GemScript collage with a small tightly cropped high-contrast vintage black-and-white film print, generous negative space, a high-lightness low-saturation Morandi paper background, multicolor flat-back rhinestone calligraphy using exact custom text, controlled mixed-shape accents, organic stroke extensions, nonlinear loose-gem clusters, a source-responsive layout, and an optional automatic 3:4 composite that stacks the effect above the untouched original. Use for GemScript, rhinestone-script, Y2K jewel-sticker, vintage-film collage, custom English word or name, effect-only, and effect-plus-original image requests.

哲学内核驱动的「无口播知识情绪片」生产：2-4 分钟、16:9 横版、无人声，中文主字幕+英文译文同屏， 全片由代码逐帧画出（Canvas/MS 路线 + seek(t) 确定性渲染 + Playwright 截帧 + ffmpeg）。 与同类 skill 的差异在内容层：五问选题门（写不出「献给每一个___的人」不立项）、 九列运动脚本级分镜表（不许一句话意图）、对标帧逆向先于写码、契约基准截图分段并行、 程序化密度自查与 impact 帧级对位。经过 90s 首跑与 135s 正片验证。 用户说「做一支 vibe 知识片 / 无口播知识短片」、给出一个概念要拍成情绪片、 或要求「哲学向知识动画」时使用。有人声口播的讲解片、剪辑已有素材、写实镜头为主的片子不适用。